Skip to content

Show a user-friendly error when no embedding model is configured #553

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
haiphucnguyen merged 1 commit into from
Jul 24, 2026
Merged

Show a user-friendly error when no embedding model is configured #553

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions shared/src/main/kotlin/io/askimo/core/providers/OpenAiCompatibleChatModelFactory.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -284,6 +284,10 @@ abstract class OpenAiCompatibleChatModelFactory<T> : ChatModelFactory<T>
override fun createEmbeddingModel(settings: T): EmbeddingModel {
val baseUrl = settings.baseUrl.removeSuffix("/")
val modelName = settings.embeddingModel.ifBlank { AppConfig.models[getProvider()].embeddingModel }
check(modelName.isNotBlank()) {
"No embedding model is configured for ${getProvider().name}. " +
"Go to Settings > AI Provider and select an embedding model under the provider configuration card."
}
checkEmbeddingAvailability(baseUrl, modelName)
return customizeEmbeddingBuilder(
settings,
Expand Down
17 changes: 12 additions & 5 deletions ...src/main/kotlin/io/askimo/core/providers/openaicompatible/OpenAiCompatibleModelFactory.kt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,11 +34,18 @@ class OpenAiCompatibleModelFactory : OpenAiCompatibleChatModelFactory<OpenAiComp
* OpenAI-compatible servers can be remote — skip the local model availability check.
* Also uses the settings API key (via [resolveApiKey]) for the embedding request itself.
*/
override fun createEmbeddingModel(settings: OpenAiCompatibleSettings): EmbeddingModel = OpenAiEmbeddingModelBuilder()
.baseUrl(settings.baseUrl)
.apiKey(resolveApiKey(settings))
.modelName(AppConfig.models[ModelProvider.OPENAI_COMPATIBLE].embeddingModel)
.build()
override fun createEmbeddingModel(settings: OpenAiCompatibleSettings): EmbeddingModel {
val modelName = AppConfig.models[ModelProvider.OPENAI_COMPATIBLE].embeddingModel
check(modelName.isNotBlank()) {
"No embedding model is configured for ${ModelProvider.OPENAI_COMPATIBLE.name}. " +
"Go to Settings > AI Provider and select an embedding model under the provider configuration card."
}
return OpenAiEmbeddingModelBuilder()
.baseUrl(settings.baseUrl)
.apiKey(resolveApiKey(settings))
.modelName(modelName)
.build()
}

override fun getEmbeddingTokenLimit(settings: OpenAiCompatibleSettings): Int {
val modelName = AppConfig.models[ModelProvider.OPENAI_COMPATIBLE].embeddingModel.lowercase()
Expand Down